sched/cpufreq: Consider reduced CPU capacity in energy calculation

Energy Aware Scheduling (EAS) needs to predict the decisions made by
SchedUtil. The map_util_freq() exists to do that.

There are corner cases where the max allowed frequency might be reduced
(due to thermal). SchedUtil as a CPUFreq governor, is aware of that
but EAS is not. This patch aims to address it.

SchedUtil stores the maximum allowed frequency in
'sugov_policy::next_freq' field. EAS has to predict that value, which is
the real used frequency. That value is made after a call to
cpufreq_driver_resolve_freq() which clamps to the CPUFreq policy limits.
In the existing code EAS is not able to predict that real frequency.
This leads to energy estimation errors.

To avoid wrong energy estimation in EAS (due to frequency miss prediction)
make sure that the step which calculates Performance Domain frequency,
is also aware of the allowed CPU capacity.

Furthermore, modify map_util_freq() to not extend the frequency value.
Instead, use map_util_perf() to extend the util value in both places:
SchedUtil and EAS, but for EAS clamp it to max allowed CPU capacity.
In the end, we achieve the same desirable behavior for both subsystems
and alignment in regards to the real CPU frequency.

Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> (For the schedutil part)
Link: https://lore.kernel.org/r/20210614191238.23224-1-lukasz.luba@arm.com

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 757fc60658fa662d51ea73f97dc5023958da428c..3f221dbf5f95d9f75b47d4758aede461fba22ad8 100644 (file)
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -91,6 +91,8 @@ void em_dev_unregister_perf_domain(struct device *dev);
  * @pd         : performance domain for which energy has to be estimated
  * @max_util   : highest utilization among CPUs of the domain
  * @sum_util   : sum of the utilization of all CPUs in the domain
+ * @allowed_cpu_cap    : maximum allowed CPU capacity for the @pd, which
+                         might reflect reduced frequency (due to thermal)
  *
  * This function must be used only for CPU devices. There is no validation,
  * i.e. if the EM is a CPU type and has cpumask allocated. It is called from
@@ -100,7 +102,8 @@ void em_dev_unregister_perf_domain(struct device *dev);
  * a capacity state satisfying the max utilization of the domain.
  */
 static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
-                               unsigned long max_util, unsigned long sum_util)
+                               unsigned long max_util, unsigned long sum_util,
+                               unsigned long allowed_cpu_cap)
 {
        unsigned long freq, scale_cpu;
        struct em_perf_state *ps;
@@ -112,11 +115,17 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
        /*
         * In order to predict the performance state, map the utilization of
         * the most utilized CPU of the performance domain to a requested
-        * frequency, like schedutil.
+        * frequency, like schedutil. Take also into account that the real
+        * frequency might be set lower (due to thermal capping). Thus, clamp
+        * max utilization to the allowed CPU capacity before calculating
+        * effective frequency.
         */
        cpu = cpumask_first(to_cpumask(pd->cpus));
        scale_cpu = arch_scale_cpu_capacity(cpu);
        ps = &pd->table[pd->nr_perf_states - 1];
+
+       max_util = map_util_perf(max_util);
+       max_util = min(max_util, allowed_cpu_cap);
        freq = map_util_freq(max_util, ps->frequency, scale_cpu);
 
        /*
@@ -209,7 +218,8 @@ static inline struct em_perf_domain *em_pd_get(struct device *dev)
        return NULL;
 }
 static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
-                       unsigned long max_util, unsigned long sum_util)
+                       unsigned long max_util, unsigned long sum_util,
+                       unsigned long allowed_cpu_cap)
 {
        return 0;
 }

diff --git a/include/linux/sched/cpufreq.h b/include/linux/sched/cpufreq.h
index 6205578ab6ee6d8fc590a2ee2372980c31b99585..bdd31ab93bc51dec77f73a5496160cac0083cfac 100644 (file)
--- a/include/linux/sched/cpufreq.h
+++ b/include/linux/sched/cpufreq.h
@@ -26,7 +26,7 @@ bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy);
 static inline unsigned long map_util_freq(unsigned long util,
                                        unsigned long freq, unsigned long cap)
 {
-       return (freq + (freq >> 2)) * util / cap;
+       return freq * util / cap;
 }
 
 static inline unsigned long map_util_perf(unsigned long util)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 4f09afd2f32110dfd8280382f2a68a64bc71df25..57124614363df6bb3db12511f66a0aa1ba14c5cb 100644 (file)
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -151,6 +151,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
        unsigned int freq = arch_scale_freq_invariant() ?
                                policy->cpuinfo.max_freq : policy->cur;
 
+       util = map_util_perf(util);
        freq = map_util_freq(util, freq, max);
 
        if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0d6d190accb093c17b5b00944763592c81e35c21..ed7df1b9cba936ae307db33685f96ad3c3a2be64 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6592,7 +6592,7 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
                max_util = max(max_util, min(cpu_util, _cpu_cap));
        }
 
-       return em_cpu_energy(pd->em_pd, max_util, sum_util);
+       return em_cpu_energy(pd->em_pd, max_util, sum_util, _cpu_cap);
 }
 
 /*